PA PANTHEON Precision Farming of Hazelnut Orchards Project ID: - - PowerPoint PPT Presentation

PA PANTHEON

Precision Farming of Hazelnut Orchards

Project ID: 774571

May 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 1

ROMA

TRE

Modern Hazelnut Farming (MHF)

Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 2

• Well-structured orchards with a

regular planting pattern

• Regular

layout allows the mechanization

• f

many field

• perations
• Typical Operations in MHF:
• Irrigation
• Pruning
• Pest and Disease Control
• Production Estimation

Hazelnut Harvesting Process (Source: FERRERO)

May 13°, 2018

ROMA

TRE

MHF – Observations

Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 3

• In current best practice decisions are made by
• 1. Dividing the large-scale orchards in sectors
• 2. Observing few representative plants per sector
• 3. Performing homogeneous treatments per sector
• This may result in

1. Product waste (economic loss) 2. Avoidable pollution (environmental damage)

Hazelnut Block in AgriChile (Source: FERRERO)

May 13°, 2018

ROMA

TRE

PANTHEON Ambition

Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 4

• To Introduce a new paradigm for

the management of large-scale hazelnut orchards

• To achieve the resolution of a

single plant in terms of

• 1. collecting information
• 2. performing (some) farming
• perations

Large Hazelnut Orchard with a 5 x 3 planting pattern (Source: FERRERO)

May 13°, 2018

Impact

Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 5

Continuous monitoring will enable a prompt detection of per-plant limiting factors and trigger focused (automatic) interventions.

1. Increase of Production by improving the general phytosanitary state of the orchard 2. Environmental-Friendly Management by 1. Reducing waste of water 2. Decreasing the need of chemical inputs 3. Reduction of Human Burden by the automatization on large scale of tedious and repetitive operations

ROMA

TRE

3D Hazelnut Wild Trees Reconstruction (Source: TRIER)

May 13°, 2018

ROMA

TRE

Approach: An Agricultural SCADA

Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 6

• Unmanned aerial and ground robots

move within an orchard to

• collect data
• perform farming operations
• An

IoT-based agro-meteorological network for environmental monitoring

• A central operative unit integrates the

collected data to

• perform

automatic feedback actions (e.g. regulate the irrigation system)

• support

the decisions

• f

the agronomists

Agricultural SCADA Concept (Source: ULB)

May 13°, 2018

ROMA

TRE

PANTHEON – A pragmatic approach

Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 7

• Objectives identified in collaboration

with agronomists of FERRERO

• We focus (only) on:
• 1. Phytosanitary status estimation
• 2. Automatic irrigation regulation
• 3. Automatic suckers’ treatment
• 4. Improvement of pruning practices
• 5. Automatic estimation of the production

05/07 02/08 30/08 06/09

Hazelnuts at different ripe stage (Source: UNITUS)

May 13°, 2018

ROMA

TRE

UAV Main Activities

March 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 8

• Data Collection for Agronomical

Indicators:

• 1. Water Stress
• 2. Pest and Disease Detection
• 3. Fruit Detection
• Typical approaches are based on

Orthomosaic Techniques

ROMA

TRE

Orthomosaic Techniques

May 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 9

Measuring process:

• Cover the area of interest using a

lawnmower pattern

• Ensure overlap between pictures

and in between bands Validation process:

• 1. Pictures correction
• 2. Band creation through matching
• 3. Bands alignment and orthomosaic

ROMA

TRE

Orthomosaic Techniques

May 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 10

Orthomosaic characteristics:

• Overlap>80%
• Higher altitude worst resolution
• Does not exploit localization accuracy
• The coverage time highly depends on the

amount of turns (bands)

Resolution: 2.5cm Resolution: 5cm 50 m 100 m

ROMA

TRE

UAV Aircraft Model

March 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 11

DJI Matrice 600 Pro

• Design: Six-rotor flying platform
• Applications: Professional aerial photography

and industrial applications

• Main Features:
• RTK Localization Accuracy (~cm)
• Triple IMU Accuracy for Flight Control

ROMA

TRE

UAV: Architecture

May 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 12

On-board computer (Trajectory Execution, Sensor Triggering, Data Collection) Thermal camera RGB camera Multispectral camera Ground computer (Trajectory Planning, Ros Enabled) Radio Communication

ROMA

TRE

Multispectral camera

March 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 13

• Model:Tetracam MCAW 6
• Features: Multi-spectral information on a pixel-by-pixel

basis

• Application: Compute vegetation spectral features to

measure the photosynthesis activity of leaves such as production capability

ROMA

TRE

Thermal camera

March 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 14

• Model: Teax ThermalCapture 2.0 640
• Features: Fully radiometric per pixel temperature data
• Application: Measurement of the leaf temperature to

detect possible water stress.

ROMA

TRE

RGB camera

March 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 15

• Model: Sony α5100
• Features: 24.3 megapixel APS-C CMOS sensor
• Application: Detect the main features of areas of

interest such as tree precise location and macro- management.

ROMA

TRE

Bulding an Orthomosaic In Our Setting

May 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 16

Outcome:

• 3 different orthomosaics

Setting Constraints:

• High resolution required (~2.5cm/pixel)
• Different FOVs (Field of view)
• Low resolution thermal camera

Thermal camera Multispectral camera RGB camera

62 m 48 m 78 m 54 m 70 m 44 m

ROMA

TRE

Building an Orthomosaic In Our Setting

May 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 17

Necessity of new techniques

A classical approach implies altitude of less than 50 m to reach the demanded constraints: To map 10 hectares:

• >2500 pictures = High amount of data
• Unnecessary resolution and pictures for RGB camera
• Excessive time (>1.5 hours)
• Several flights required ( >6 flights)

ROMA

TRE

A change of Perspective

May 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 18

Observations:

• UAV High Localization Accuracy
• Regular disposition of the trees
• Presence of non-interesting areas

Objective:

• Reduce Coverage Time
• Reduce Amount Data

Hazelnut plantation (Source: UNITUS) Regular pattern

ROMA

TRE

Research Challenges

May 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 19

UAV High Localization Accuracy Idea: Reduce the picture overlap. Advantages:

• Reduced coverage time by

minimizing the number of bands;

• Reduced amount of data by avoid
• versampling (up to 16 times with

80% overlap, 4 bands)

80% 60%

ROMA

TRE

• Reduced coverage time by avoiding

non-essential bands;

• Reduced amount of data by only

covering the necessary areas.

Research Challenges

May 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 20

Idea: Adaptive measurement strategies focused only on points of interests (trees).

• Varying accuracy w.r.t. areas of interest;
• No necessity of matching bands.

Advantages:

Non-interesting area Non-interesting area

ROMA

TRE

Research Challenges

May 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 21

Idea: Information-based Adaptive UAV trajectory planning using different altitude flights.

• First high altitude flight for anomalies detection
• nly.
• Second less altitude flight at reduced speed to

inspect specific areas of interest.

First flight Second flight

• Reduced coverage time by increasing altitude

(=less bands);

• Reduced amount of data by chancing spatial

resolution of the acquisition.

Advantages:

ROMA

TRE

May 13°, 2018 Workshop on Small UAVs for Precision Agriculture, Monte Roberto, Italy – Andrea Gasparri 22

Thanks for your attention! ;-)

• Prof. Emanuele Garone

egarone@ulb.ac.be

• Prof. Thomas Udelhoven

udelhove@uni-trier.de

• Prof. Andrea Gasparri

gasparri@dia.uniroma3.it